51 to 75 of 263 Human-in-the-Loop Jobs in England

view grounded in delivery experience. Embedding AI governance, observability, and responsible AI into design as first-class concerns - audit logging, human-in-the-loop escalation, grounding/hallucination controls, brand safety, and performance monitoring. Providing technical leadership to delivery teams — guiding engineers, reviewing technical decisions ...

view grounded in delivery experience Embedding responsible AI and governance principles into agentic delivery programmes — including auditability, explainability, and human-in-the-loop mechanisms Contributing to Accenture Song's commerce delivery capability — including shaping accelerators, reusable assets, delivery standards, and points of view that advance ...

stateful multi-agent workflows using Google ADK , LangChain, LangGraph, AWS Bedrock, or equivalent technologies, incorporating structured outputs, tool calling, and human-in-the-loop steps. Evaluation & Benchmarking: Implement automated offline and online evaluation suites using tools such as Braintrust, AgentCore Eval, equivalent industry solutions, or custom ...

powered solutions. Design, implement, and maintain evaluation frameworks for AI systems, including regression testing, evaluation datasets, LLM‐as‐judge methodologies, and human‐in‐the‐loop review processes. Ensure AI‐powered software solutions meet the same standards for quality, reliability, security, and testing as traditional software ...

customers across regions/time zones, with travel as required. Act as a trusted technical advisor on agentic-AI adoption with human-in-the-loop, governed approaches. Bring field learnings back to product and engineering based on real usage. Contribute pragmatic engineering standards — CI/ ...

function calling, Model Context Protocol (MCP), and agent orchestration AI Evaluation & Quality: Eval harnesses and golden datasets, LLM-as-judge and human-in-the-loop review, regression suites, and red-teaming Observability & Monitoring: Prometheus, Grafana, Datadog, Splunk, Elastic/ELK, OpenTelemetry, including GenAI tracing and token ...

Gather business requirements, high-level user stories, and acceptance criteria for AI agent workflows — including agent actions, guardrails, escalation paths, and human-in-the-loop checkpoints Assess data readiness for AI use cases (data quality, identity resolution, harmonisation) in partnership with data engineering teams supporting ...

Gather business requirements, high-level user stories, and acceptance criteria for AI agent workflows — including agent actions, guardrails, escalation paths, and human-in-the-loop checkpoints Assess data readiness for AI use cases (data quality, identity resolution, harmonisation) in partnership with data engineering teams supporting ...

in building production-grade agentic systems, using orchestration harnesses such as LangGraph to design multi-step workflows, tool use and human-in-the-loop controlsMake evaluation a first-class engineering discipline for LLM and agent work. That means curated eval sets, LLM-as-judge ...

actions. Advise on secure patterns for AI application development, including permission boundaries, identity controls, sandboxing, auditability, input/output validation and human-in-the-loop controls. Help clients establish governance and assurance processes for AI systems across the lifecycle, from experimentation through to production deployment. ...

prompt change made things better or worse. Design Agentic Workflows: Architect multi-step, tool-using pipelines with explicit state, guardrails, and human-in-the-loop review where the stakes demand it. Lead Innovation: Push the envelope with cutting-edge LLM and agentic techniques ...

autonomous agents in production; MCP servers and clients; orchestration frameworks such asLangGraph,PydanticAI, or provider-native SDKs; sandboxing,permissioning, and human-in-the-loop design Retrieval and knowledge: RAG and Graph RAG at enterprise scale; vector and hybrid search (pgvector, OpenSearch/Elasticsearch, or dedicated ...

versus-buy. Oversee the development of safe and reliable agents. Ensure our agents have well-scoped tool permissions, guardrails and human-in-the-loop controls, and are evaluated end to end before and after release. Ensure quality, security and compliance. Set standards for code quality ...

operating production large language model and machine learning workloads with attention to cost, latency, performance, security, and scaling Experience integrating human‐in‐the‐loop and user feedback signals into iterative improvement, including active learning, preference signals, and labeling strategies #J-18808-Ljbffr ...

actions. Advise on secure patterns for AI application development, including permission boundaries, identity controls, sandboxing, auditability, input/output validation and human‐in‐the‐loop controls. Help clients establish governance and assurance processes for AI systems across the lifecycle, from experimentation through to production deployment. ...

stateful multi‐agent workflows using Google ADK , LangChain, LangGraph, AWS Bedrock, or equivalent technologies, incorporating structured outputs, tool calling, and human‐in‐the‐loop steps. Evaluation & Benchmarking: Implement automated offline and online evaluation suites using tools such as Braintrust, AgentCore Eval, equivalent industry solutions, or custom ...

authorized AI capabilities within the work environment to accelerate architecture analysis, option evaluation, and delivery of strategic global solutions, with human-in-the-loop validation and appropriate handling of sensitive data Actively contributes to the engineering community as an advocate of firmwide frameworks, tools ...

authorized AI capabilities within the work environment to accelerate architecture analysis, option evaluation, and delivery of strategic global solutions, with human-in-the-loop validation and appropriate handling of sensitive data Actively contributes to the engineering community as an advocate of firmwide frameworks, tools ...

ready to design and build. You'll work on our core product and tackle exciting engineering challenges across extraction, workflow orchestration, human-in-the-loop review, evaluation, and production reliability. What you will be doing: Design, build and ship production-grade agentic AI systems that handle ...

postgraduate degree is valued but not required. NICE TO HAVE Experience building agentic products, including orchestration, memory, tool calling and human-in-the-loop controls. Document understanding, OCR and table extraction on complex financial documents. Fine-tuning or distillation of language models, and inference optimisation. Experience ...

powered systems(RAG, fine-tuning, tool use, multi-agent orchestration) Developagentic workflowsfor automation, reasoning, and conversational experiences Define patterns forautonomous + human-in-the-loop systems Build and scale solutions on theAzure AI stack(Azure OpenAI, AI Studio, Azure ML, Cognitive Services) Create reusable infrastructure:Prompt ...

the tools, APIs and data services that agents call, creating clear contracts, predictable failure modes and full auditability. Engineer guardrails, human-in-the-loop checkpoints and fallbacks for high-stakes automated decisions. Instrument, monitor and troubleshoot agents and services in production, including tracing, cost ...

Research and delivery excellence Help define the evaluation strategy and methodology for AI capabilities across the company - automated metrics, human-in-the-loop workflows, test set management, and benchmarking - and establish the quality standards other teams build against. Build evaluation frameworks and developer ...

native development tooling (e.g. GitHub Copilot, Claude Code, Cursor, or equivalent) across engineering organisations.Understanding of agentic software delivery patterns: autonomous agents, human-in-the-loop workflows, agentic code review, test generation, and AI-assisted architecture.Ability to define governance frameworks that enable AI-augmented development at pace ...

access, tool use, model access, approvals, auditability and policy enforcement. Establish engineering standards for agent orchestration, memory and context, tool integration, human‐in‐the‐loop controls, evaluation, observability and operational support. Ensure security, compliance, resilience, cost management and operational readiness are designed into the platform ...